Muennighoff's picture
Add eval
990f338
raw
history blame
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.335,
"acc_stderr": 0.014933117490932579
},
"anli_r2": {
"acc": 0.356,
"acc_stderr": 0.015149042659306621
},
"anli_r3": {
"acc": 0.31833333333333336,
"acc_stderr": 0.013452948996996292
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.0672477765493766,
"f1": 0.2986425339366516
},
"copa": {
"acc": 0.64,
"acc_stderr": 0.048241815132442176
},
"hellaswag": {
"acc": 0.37641904003186616,
"acc_stderr": 0.0048349694128836315,
"acc_norm": 0.4523999203345947,
"acc_norm_stderr": 0.004967118575905289
},
"rte": {
"acc": 0.5234657039711191,
"acc_stderr": 0.030063300411902652
},
"winogrande": {
"acc": 0.4996053670086819,
"acc_stderr": 0.014052481306049516
},
"storycloze_2016": {
"acc": 0.6306787814003206,
"acc_stderr": 0.011160545865067166
},
"boolq": {
"acc": 0.4941896024464832,
"acc_stderr": 0.008744464477761504
},
"arc_easy": {
"acc": 0.47769360269360267,
"acc_stderr": 0.010249568404555636,
"acc_norm": 0.45454545454545453,
"acc_norm_stderr": 0.010217299762709433
},
"arc_challenge": {
"acc": 0.2363481228668942,
"acc_stderr": 0.012414960524301834,
"acc_norm": 0.2525597269624573,
"acc_norm_stderr": 0.012696728980207706
},
"sciq": {
"acc": 0.714,
"acc_stderr": 0.01429714686251791,
"acc_norm": 0.696,
"acc_norm_stderr": 0.01455320568795043
},
"piqa": {
"acc": 0.6828073993471164,
"acc_stderr": 0.01085815545438087,
"acc_norm": 0.6789989118607181,
"acc_norm_stderr": 0.010892641574707906
}
},
"versions": {
"anli_r1": 0,
"anli_r2": 0,
"anli_r3": 0,
"cb": 1,
"copa": 0,
"hellaswag": 0,
"rte": 0,
"winogrande": 0,
"storycloze_2016": 0,
"boolq": 1,
"arc_easy": 0,
"arc_challenge": 0,
"sciq": 0,
"piqa": 0
}
}